A Hybrid ANN coupled NTOPSIS Approach: An Intelligent Multi-Objective Framework for solving Engineering Problems

Abstract

Optimization is a group of mathematical strategies for resolving quantitative issues in a variety of fields. The industries are relentlessly working to optimize more than one objective which are often conflicting in nature. Hence researchers are shifting their focus towards the multi-objective optimization algorithm which computes a set of Non-dominated solutions (NDS) which predominates other solutions in the search space. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is one such multi-objective optimization algorithm but it fails to compute an accurate result when applied to rocky datasets. In order to overcome the difficulties, we have integrated the Artificial Neural Network (ANN) and TOPSIS with NSGA-II. The ANN algorithm creates the objective functions and the TOPSIS algorithm creates a trade-off between the NDS for better exploration. For testing the applicability of our approach we have applied it for computing the machining parameters for turning Aluminum alloy 6061-T6 using a high speed steel tool so that the objective performances namely machining time, material removal rate (MRR) and surface roughness (SR) are optimized. For validating the approach two experiments are conducted at the optimized parameters and the parameters obtained by the traditional NSGA-II approach. The computed the relative error (RAE) between the simulated and the first experimental values which is 1.87% for machining time, 4.2% for MRR and 4.3% for SR and the simulated and the second experimental values which is 14.8% for machining time, 12% for MRR and 11.2% for SR. The RAE value is very less and within the acceptable limit for the result computed by the proposed approach. The strength of our proposed algorithm is its practical applicability and ability to provide an accurate solution to an industry problem and hence our model is suitable for industrial applications.